Method, device, electronic device and storage medium for matching supply and demand products

Abstract

The present application proposes a matching method, device, electronic device and storage medium for supply and demand products, wherein the matching method includes: obtaining supply and demand product pairs, the supply and demand product pairs including demand products to be recommended and supply products to be recommended; calculating product similarity scores for the supply and demand product pairs; calculating enterprise similarity scores for the supply and demand product pairs; and generating a target supply and demand product pair list based on the product similarity scores and enterprise similarity scores. Thus, the influence of product similarity scores and enterprise similarity scores on supply and demand matching can be comprehensively considered, and a target supply and demand product pair list can be automatically generated based on product similarity scores and enterprise similarity scores, so that enterprises can quickly and accurately obtain supply and demand product pairs with high product matching, which helps to improve the operational efficiency of enterprises.

Description

Technical Field

[0001] The present application relates to the technical field of supply and demand matching, and in particular to a method, device, electronic device and storage medium for matching supply and demand products. Background Art

[0002] Supply and demand matching refers to the matching of products released between product demanders and product suppliers, which is crucial to the normal operation of enterprises. If supply and demand matching cannot be obtained accurately and quickly, it may affect the production progress of the enterprise and increase procurement costs for product demanders, and may cause serious inventory backlogs for product suppliers. At present, most of the supply and demand matching methods in related technologies rely on manual verification, which is time-consuming and has high labor costs. Summary of the invention

[0003] The present application aims to solve one of the technical problems in the related art at least to some extent.

[0004] To this end, the first embodiment of the present application proposes a method for matching supply and demand products, obtaining supply and demand product pairs, the supply and demand product pairs including demand products to be recommended and supply products to be recommended, calculating product similarity scores for the supply and demand product pairs, calculating enterprise similarity scores for the supply and demand product pairs, and generating a target supply and demand product pair list based on the product similarity scores and enterprise similarity scores. Thus, the impact of product similarity scores and enterprise similarity scores on supply and demand matching can be comprehensively considered, and a target supply and demand product pair list can be automatically generated based on product similarity scores and enterprise similarity scores, so that enterprises can quickly and accurately obtain supply and demand product pairs with high product matching, which helps to improve the operational efficiency of enterprises.

[0005] The second embodiment of the present application proposes a device for matching supply and demand products.

[0006] A third aspect of the present application provides an electronic device.

[0007] The fourth aspect of the present application provides a computer-readable storage medium.

[0008] The first aspect of the present application proposes a method for matching supply and demand products, including: obtaining a supply and demand product pair, the supply and demand product pair including a demand product to be recommended and a supply product to be recommended; calculating a product similarity score for the supply and demand product pair; calculating a company similarity score for the supply and demand product pair; and generating a target supply and demand product pair list based on the product similarity score and the company similarity score.

[0009] According to the supply and demand product matching method of the embodiment of the present application, a supply and demand product pair is obtained, the supply and demand product pair includes a demand product to be recommended and a supply product to be recommended, the product similarity score of the supply and demand product pair is calculated, the enterprise similarity score of the supply and demand product pair is calculated, and a target supply and demand product pair list is generated according to the product similarity score and the enterprise similarity score. Thus, the influence of the product similarity score and the enterprise similarity score on the supply and demand matching can be comprehensively considered, and a target supply and demand product pair list can be automatically generated according to the product similarity score and the enterprise similarity score, so that the enterprise can quickly and accurately obtain supply and demand product pairs with high product matching, which helps to improve the operational efficiency of the enterprise.

[0010] In addition, the method for matching supply and demand products according to the above embodiment of the present application may also have the following additional technical features:

[0011] In one embodiment of the present application, the enterprise similarity score includes at least one of the following scores: an enterprise credit score, an enterprise historical preference score, and an enterprise transportation cost score.

[0012] In one embodiment of the present application, calculating the enterprise historical preference score of the supply-demand product pair includes: obtaining historical browsing click data of the enterprise corresponding to the supply-demand product pair; and calculating the enterprise historical preference score based on the historical browsing click data.

[0013] In one embodiment of the present application, calculating the enterprise transportation cost score of the supply and demand product pair includes: obtaining the spatial distance from the enterprise corresponding to the supply and demand product pair to the target enterprise; and calculating the enterprise transportation cost score based on the spatial distance.

[0014] In one embodiment of the present application, generating a target supply and demand product pair list based on the product similarity score and the enterprise similarity score includes: screening out target supply and demand product pairs from the supply and demand product pairs based on the product similarity score and the enterprise similarity score; calculating a total similarity score of the target supply and demand product pairs based on the product similarity score and the enterprise similarity score; and sorting the target supply and demand product pairs based on the total similarity score to generate the target supply and demand product pair list.

[0015] In one embodiment of the present application, the calculating of the product similarity score of the supply-demand product pair includes: calculating the product similarity score of the supply-demand product pair according to the first name of the demand product to be recommended and the second name of the supply product to be recommended.

[0016] In one embodiment of the present application, the product similarity score of the supply and demand product pair is calculated based on the first name of the demand product to be recommended and the second name of the supply product to be recommended, including: performing word segmentation processing on the first name and the second name respectively to obtain multiple word segments; generating a first vector of the demand product to be recommended and a second vector of the supply product to be recommended based on the word segments; and calculating the product similarity score based on the first vector and the second vector.

[0017] In one embodiment of the present application, generating the first vector of the demand product to be recommended and the second vector of the supply product to be recommended based on the word segmentation includes: calculating the first word frequency of the word segmentation corresponding to the first name and the second word frequency of the word segmentation corresponding to the second name; calculating the first inverse document frequency of the word segmentation corresponding to the first name and the second inverse document frequency of the word segmentation corresponding to the second name; generating the first vector based on the first word frequency and the first inverse document frequency; generating the second vector based on the second word frequency and the second inverse document frequency.

[0018] In one embodiment of the present application, calculating the product similarity score according to the first vector and the second vector includes: calculating the cosine similarity between the first vector and the second vector; and generating the product similarity score according to the cosine similarity.

[0019] In one embodiment of the present application, it also includes: acquiring first attribute information of the demand product and second attribute information of the supply product; and screening out the supply and demand product pairs from the demand product and the supply product based on the first attribute information and the second attribute information.

[0020] In one embodiment of the present application, the first attribute information includes at least one of the following information: demand price range, demand deadline and demand spot information; the second attribute information includes at least one of the following information: supply price range, delivery time and supply spot information.

[0021] The second aspect of the present application proposes a matching device for supply and demand products, including: an acquisition module, used to acquire supply and demand product pairs, the supply and demand product pairs including demand products to be recommended and supply products to be recommended; a first calculation module, used to calculate the product similarity score of the supply and demand product pairs; a second calculation module, used to calculate the enterprise similarity score of the supply and demand product pairs; a generation module, used to generate a target supply and demand product pair list according to the product similarity score and the enterprise similarity score.

[0022] The matching device for supply and demand products of the embodiment of the present application obtains supply and demand product pairs, the supply and demand product pairs include demand products to be recommended and supply products to be recommended, calculates product similarity scores for the supply and demand product pairs, calculates enterprise similarity scores for the supply and demand product pairs, and generates a target supply and demand product pair list based on the product similarity scores and enterprise similarity scores. Thus, the influence of product similarity scores and enterprise similarity scores on supply and demand matching can be comprehensively considered, and a target supply and demand product pair list can be automatically generated based on product similarity scores and enterprise similarity scores, so that enterprises can quickly and accurately obtain supply and demand product pairs with high product matching, which helps to improve the operational efficiency of enterprises.

[0023] In one embodiment of the present application, the enterprise similarity score includes at least one of the following scores: an enterprise credit score, an enterprise historical preference score, and an enterprise transportation cost score.

[0024] In one embodiment of the present application, the second calculation module is specifically used to: obtain historical browsing click data of the enterprise corresponding to the supply and demand product pair; and calculate the historical preference score of the enterprise based on the historical browsing click data.

[0025] In one embodiment of the present application, the second calculation module is specifically used to: obtain the spatial distance from the enterprise corresponding to the supply and demand product pair to the target enterprise; and calculate the enterprise transportation cost score based on the spatial distance.

[0026] In one embodiment of the present application, the generation module is specifically used to: filter out target supply and demand product pairs from the supply and demand product pairs according to the product similarity scores and the enterprise similarity scores; calculate the total similarity scores of the target supply and demand product pairs according to the product similarity scores and the enterprise similarity scores; sort the target supply and demand product pairs according to the total similarity scores to generate the target supply and demand product pair list.

[0027] In one embodiment of the present application, the first calculation module is specifically used to calculate the product similarity score of the supply and demand product pair according to the first name of the demand product to be recommended and the second name of the supply product to be recommended.

[0028] In one embodiment of the present application, the first calculation module includes: a word segmentation unit, used to perform word segmentation on the first name and the second name respectively to obtain multiple word segments; a generation unit, used to generate a first vector of the demand product to be recommended and a second vector of the supply product to be recommended according to the word segments; a calculation unit, used to calculate the product similarity score according to the first vector and the second vector.

[0029] In one embodiment of the present application, the generating unit is specifically used to: calculate a first word frequency of the word segment corresponding to the first name and a second word frequency of the word segment corresponding to the second name; calculate a first inverse document frequency of the word segment corresponding to the first name and a second inverse document frequency of the word segment corresponding to the second name; generate the first vector according to the first word frequency and the first inverse document frequency; generate the second vector according to the second word frequency and the second inverse document frequency.

[0030] In one embodiment of the present application, the calculation unit is specifically used to: calculate the cosine similarity between the first vector and the second vector; and generate the product similarity score according to the cosine similarity.

[0031] In one embodiment of the present application, the acquisition module is specifically used to: acquire first attribute information of the demand product and second attribute information of the supply product; and filter out the supply and demand product pairs from the demand product and the supply product based on the first attribute information and the second attribute information.

[0032] In one embodiment of the present application, the first attribute information includes at least one of the following information: demand price range, demand deadline and demand spot information; the second attribute information includes at least one of the following information: supply price range, delivery time and supply spot information.

[0033] The third aspect of the present application provides an electronic device, comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the method for matching supply and demand products as described in the first aspect of the present application is implemented.

[0034] The electronic device of the embodiment of the present application executes a computer program stored in a memory through a processor to obtain a supply and demand product pair, the supply and demand product pair includes a demand product to be recommended and a supply product to be recommended, calculates a product similarity score of the supply and demand product pair, calculates a corporate similarity score of the supply and demand product pair, and generates a target supply and demand product pair list based on the product similarity score and the corporate similarity score. Thus, the influence of the product similarity score and the corporate similarity score on the supply and demand matching can be comprehensively considered, and a target supply and demand product pair list can be automatically generated based on the product similarity score and the corporate similarity score, so that the enterprise can quickly and accurately obtain a supply and demand product pair with a high product matching degree, which helps to improve the operational efficiency of the enterprise.

[0035] The fourth aspect of the present application provides a computer-readable storage medium on which a computer program is stored. When the program is executed by a processor, the scheduled task startup method described in the aforementioned method embodiment is implemented.

[0036] The computer-readable storage medium of the embodiment of the present application obtains supply and demand product pairs by storing a computer program and being executed by a processor, wherein the supply and demand product pairs include demand products to be recommended and supply products to be recommended, calculates product similarity scores of the supply and demand product pairs, calculates enterprise similarity scores of the supply and demand product pairs, and generates a target supply and demand product pair list based on the product similarity scores and enterprise similarity scores. Thus, the influence of product similarity scores and enterprise similarity scores on supply and demand matching can be comprehensively considered, and a target supply and demand product pair list can be automatically generated based on product similarity scores and enterprise similarity scores, so that enterprises can quickly and accurately obtain supply and demand product pairs with high product matching, which helps to improve the operational efficiency of enterprises.

[0037] Additional aspects and advantages of the present application will be given in part in the following description, and in part will become apparent from the following description, or will be learned through practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] The above and / or additional aspects and advantages of the present application will become apparent and easily understood from the following description of the embodiments in conjunction with the accompanying drawings, in which:

[0039] Figure 1 A schematic diagram of a flow chart of a method for matching supply and demand products according to an embodiment of the present application;

[0040] Figure 2 A schematic diagram of a process for obtaining supply and demand product pairs in a supply and demand product matching method according to an embodiment of the present application;

[0041] Figure 3 A schematic diagram of a flow chart of selecting supply and demand product pairs from demand products and supply products in a supply and demand product matching method according to an embodiment of the present application;

[0042] Figure 4 A schematic diagram of a flow chart of calculating a product similarity score of a supply-demand product pair in a supply-demand product matching method according to an embodiment of the present application;

[0043] Figure 5 A schematic diagram of a process for generating a target supply-demand product pair list in a supply-demand product matching method according to an embodiment of the present application;

[0044] Figure 6 A schematic diagram of a flow chart of a method for matching supply and demand products according to another embodiment of the present application;

[0045] Figure 7 A schematic diagram of the structure of a supply and demand product matching system according to an embodiment of the present application;

[0046] Figure 8 This is a structural schematic diagram of a device for matching supply and demand products according to another embodiment of the present application;

[0047] Fig. 9 A schematic diagram of the structure of a device for matching supply and demand products according to another embodiment of the present application; and

[0048] Fig.10 It is a schematic diagram of the structure of an electronic device according to an embodiment of the present application. DETAILED DESCRIPTION

[0049] Embodiments of the present application are described in detail below, and examples of the embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are intended to be used to explain the present application, and should not be construed as limiting the present application.

[0050] The following describes the supply and demand product matching method, device, electronic device and storage medium of the embodiments of the present application with reference to the accompanying drawings.

[0051] Figure 1 The present invention is a flowchart of a method for matching supply and demand products according to an embodiment of the present application.

[0052] like Figure 1 As shown, the method for matching supply and demand products in the embodiment of the present application may include the following steps:

[0053] S101, obtaining a supply-demand product pair, where the supply-demand product pair includes a demand product to be recommended and a supply product to be recommended.

[0054] It should be noted that the execution subject of the matching method of supply and demand products in the embodiment of the present application may be a matching device of supply and demand products, and the matching device of supply and demand products in the embodiment of the present application may be configured in any electronic device so that the electronic device can execute the matching method of supply and demand products in the embodiment of the present application. Among them, the electronic device may be a personal computer (PC for short), a cloud device, a mobile device, etc., and the mobile device may be, for example, a mobile phone, a tablet computer, a personal digital assistant, a wearable device, a vehicle-mounted device, and other hardware devices with various operating systems, touch screens, and / or display screens.

[0055] Optionally, the demand products to be recommended may be obtained from the product demanders, and the supply products to be recommended may be obtained from the product suppliers. For example, the product demanders and product suppliers may log in to the third-party platform respectively, and publish the demand products or supply products to be recommended on the third-party platform. The third-party platform may summarize the demand products and supply products to be recommended published by the product demanders and product suppliers, and obtain the supply and demand product pairs according to the preset corresponding relationship.

[0056] It is understandable that there can be one or more product demanders and product suppliers, and there can be one or more demand products to be recommended and supply products to be recommended. It should be noted that in the embodiments of the present application, the types of demand products to be recommended and supply products to be recommended are not limited.

[0057] S102, calculating the product similarity score of the supply and demand product pairs.

[0058] In the embodiment of the present application, the product similarity score of the supply and demand product pair can be calculated. It is understandable that different supply and demand product pairs may correspond to different product similarity scores, and the higher the product similarity score, the higher the product similarity between the demand product to be recommended and the supply product to be recommended in the corresponding supply and demand product pair.

[0059] Optionally, calculating the product similarity score of the supply and demand product pair may include calculating the product similarity score of the supply and demand product pair based on the first name of the demand product to be recommended and the second name of the supply product to be recommended. For example, if the first name of the demand product A to be recommended is "LCD TV" and the second name of the supply product B to be recommended is "eye protection TV", then the product similarity score of the supply and demand product pair "demand product A-supply product B" may be calculated based on "LCD TV" and "eye protection TV".

[0060] It can be understood that if the first name of the demand product to be recommended is relatively similar to the second name of the supply product to be recommended, the product similarity score of the supply and demand product pair is also relatively high.

[0061] Optionally, the first name of the demand product to be recommended and the second name of the supply product to be recommended may be input into a similarity scoring model to obtain a product similarity score of the supply and demand product pair. The similarity scoring model may be set according to actual conditions, for example, it may be a deep learning model.

[0062] S103, calculating the enterprise similarity score of the supply and demand product pairs.

[0063] In the embodiment of the present application, the enterprise similarity score of the supply and demand product pair can be calculated. It is understandable that different supply and demand product pairs may correspond to different enterprise similarity scores, and the higher the enterprise similarity score, the higher the enterprise similarity between the product demander and the product supplier in the corresponding supply and demand product pair.

[0064] It can be understood that the types of enterprise similarity scores may include one or more types.

[0065] Optionally, the enterprise similarity score includes at least one of the following scores: enterprise credit score, enterprise historical preference score and enterprise transportation cost score. It is understandable that the enterprise credit score, enterprise historical preference score and enterprise transportation cost respectively consider the three dimensions of enterprise credit, historical preference and transportation cost.

[0066] Optionally, the enterprise credit score can be determined according to the enterprise credit rating. It is understandable that the higher the enterprise credit rating, the higher the enterprise credit score.

[0067] Optionally, calculating the enterprise historical preference score of the candidate supply-demand product pair may include obtaining historical browsing and clicking data of the enterprise corresponding to the candidate supply-demand product pair, and calculating the enterprise historical preference score based on the historical browsing and clicking data. For example, if enterprise A often browses and clicks on the relevant content of enterprise B, then enterprise A has a higher historical preference score for enterprise B.

[0068] For example, the following formula can be used to calculate the enterprise historical preference score for a candidate supply and demand product pair: S his is the historical preference score for an enterprise, L is the number of views and clicks on a certain enterprise, and S is the total number of views and clicks.

[0069] Optionally, calculating the enterprise transportation cost score of the candidate supply and demand product pair may include obtaining the spatial distance between the enterprise corresponding to the candidate supply and demand product pair and the target enterprise, and calculating the enterprise transportation cost score according to the spatial distance. Generally, the enterprise corresponding to the candidate supply and demand product pair is the product supplier, and the target enterprise is the product demander.

[0070] For example, the enterprise transportation cost score for a candidate supply and demand product pair can be calculated using the following formula: S traf is the enterprise transportation cost score, dis is the spatial distance from the enterprise to the target enterprise, and dis min is the shortest distance from the enterprise to the target enterprise, dis max The maximum distance from one enterprise to the target enterprise.

[0071] S104: Generate a target supply-demand product pair list according to the product similarity scores and the enterprise similarity scores.

[0072] Optionally, generating a list of target supply and demand product pairs based on product similarity scores and enterprise similarity scores may include sorting the product similarity scores from high to low, obtaining candidate supply and demand product pairs corresponding to the top N product similarity scores, and sorting the enterprise similarity scores of the N candidate supply and demand product pairs from high to low, obtaining target supply and demand product pairs corresponding to the top M enterprise similarity scores, and then generating a list of target supply and demand product pairs. Among them, N and M can be set according to actual conditions, and M≤N. Therefore, this method can filter out target supply and demand product pairs with higher product similarity scores and enterprise similarity scores from all supply and demand product pairs.

[0073] Optionally, generating a list of target supply and demand product pairs based on product similarity scores and enterprise similarity scores may also include obtaining candidate supply and demand product pairs corresponding to product similarity scores with product similarity scores greater than a preset first threshold from all supply and demand product pairs, and then obtaining target supply and demand product pairs corresponding to enterprise similarity scores with enterprise similarity scores greater than a preset second threshold from all candidate supply and demand product pairs. The preset first threshold and the preset second threshold may be set according to actual conditions. Thus, the method can filter out target supply and demand product pairs with higher product similarity scores and enterprise similarity scores from all supply and demand product pairs.

[0074] In summary, according to the supply and demand product matching method of the embodiment of the present application, a supply and demand product pair is obtained, the supply and demand product pair includes a demand product to be recommended and a supply product to be recommended, the product similarity score of the supply and demand product pair is calculated, the enterprise similarity score of the supply and demand product pair is calculated, and a target supply and demand product pair list is generated according to the product similarity score and the enterprise similarity score. Thus, the impact of the product similarity score and the enterprise similarity score on the supply and demand matching can be comprehensively considered, and a target supply and demand product pair list can be automatically generated according to the product similarity score and the enterprise similarity score, so that the enterprise can quickly and accurately obtain supply and demand product pairs with a high product matching degree, which helps to improve the operational efficiency of the enterprise.

[0075] It is understandable that, assuming that all possible supply and demand product pairs generated from the demand products to be recommended and the supply products to be recommended are used to calculate the corresponding product similarity scores, if the number of all possible supply and demand product pairs is large, the amount of calculation consumed is also large, and the supply and demand product matching efficiency is also low. For example, assuming that there are M demand products to be recommended and N supply products to be recommended, then all possible supply and demand product pairs are M*N.

[0076] In order to solve the above problems, Figure 2 As shown, obtaining the supply and demand product pairs in step S101 may include:

[0077] S201, obtaining first attribute information of demand products and second attribute information of supply products.

[0078] Optionally, the first attribute information of the demand product to be recommended may be obtained from the product demander, and the second attribute information of the supply product to be recommended may be obtained from the product supplier. For example, both the product demander and the product supplier may log in to a third-party platform respectively, and publish the demand product or supply product to be recommended on the third-party platform, and the product demander may publish the first attribute information of the demand product when publishing the demand product to be recommended, and correspondingly, the product supplier may publish the second attribute information of the supply product when publishing the supply product to be recommended.

[0079] Optionally, the first attribute information includes at least one of the following information: demand price range, demand deadline and demand spot information. The second attribute information includes at least one of the following information: supply price range, delivery time and supply spot information.

[0080] S202: Filter out supply and demand product pairs from demand products and supply products according to the first attribute information and the second attribute information.

[0081] In an embodiment of the present application, selecting supply and demand product pairs from demand products and supply products based on the first attribute information and the second attribute information may include obtaining supply and demand product pairs that match the first attribute information and the second attribute information.

[0082] For example, if the demand price range of the demand product A to be recommended is 50 to 90 yuan, the supply price range of the supply product B to be recommended is 60 to 70 yuan, and the supply price range of the supply product C to be recommended is 100 to 150 yuan, it can be seen that the demand price range of the demand product A to be recommended and the supply price range of the supply product B to be recommended are highly matched, and "demand product A-supply product B" can be used as a supply and demand product pair. It can be seen that the demand price range of the demand product A to be recommended and the supply price range of the supply product C to be recommended are less matched, and "demand product A-supply product C" can be not used as a supply and demand product pair.

[0083] Therefore, the method can obtain the first attribute information of the demand product and the second attribute information of the supply product, and screen out supply and demand product pairs from the demand product and the supply product based on the first attribute information and the second attribute information, so that supply and demand product pairs with a high matching degree can be screened out based on the product attribute information, which can effectively reduce the number of supply and demand product pairs, and then reduce the amount of calculation, thereby improving the matching efficiency of supply and demand products.

[0084] Based on any of the above embodiments, Figure 3As shown, when the first attribute information includes at least one of the following information: demand price range, demand deadline and demand spot information, and the second attribute information includes at least one of the following information: supply price range, delivery time and supply spot information, in step S202, selecting supply and demand product pairs from the demand products and the supply products according to the first attribute information and the second attribute information may include:

[0085] S301, determine whether the demand price range and the supply price range match.

[0086] If yes, execute step S302; if no, execute step S305.

[0087] In the embodiment of the present application, it is possible to first determine whether the demand price range and the supply price range match based on the demand price range and the supply price range. It is understandable that if the demand price range and the supply price range match, it is possible to continue to determine whether other product attribute information matches. If the demand price range and the supply price range do not match, it is not necessary to determine whether other product attribute information matches, and the supply and demand product pair can be directly not retained.

[0088] Optionally, if the intersection of the demand price range and the supply price range is not empty, it can be determined that the demand price range and the supply price range match; if the intersection of the demand price range and the supply price range is empty, it can be determined that the demand price range and the supply price range do not match.

[0089] For example, if the demand price range of the recommended demand product A is 50 to 90 yuan, the supply price range of the recommended supply product B is 60 to 70 yuan, and the supply price range of the recommended supply product C is 100 to 150 yuan, it can be known that the intersection of the demand price range of the recommended demand product A and the supply price range of the recommended supply product B is 60 to 70 yuan. It can be determined that the demand price range of the recommended demand product A matches the supply price range of the recommended supply product B, and whether other product attribute information of the recommended demand product A and the recommended supply product B matches can be further determined.

[0090] In addition, it can be seen that the intersection of the demand price range of the demand product A to be recommended and the supply price range of the supply product C to be recommended is empty. It can be judged that the demand price range of the demand product A to be recommended and the supply price range of the supply product C to be recommended do not match, and the supply and demand product pair can be directly not retained.

[0091] S302, determining whether the demand deadline and the delivery time match.

[0092] If yes, execute step S303; if no, execute step S305.

[0093] In the embodiment of the present application, after determining that the demand price range matches the supply price range, it is possible to continue to determine whether the demand deadline and the delivery time match. It is understandable that if the demand deadline and the delivery time match, it is possible to continue to determine whether other product attribute information matches. If the demand deadline and the delivery time do not match, it is not necessary to determine whether other product attribute information matches, and the supply and demand product pair can be directly not retained.

[0094] Optionally, if the demand deadline is earlier than the earliest time point of the delivery time, it can be determined that the demand deadline and the delivery time do not match. Conversely, if the demand deadline is later than the earliest time point of the delivery time, it can be determined that the demand deadline and the delivery time match.

[0095] For example, if the demand deadline for the recommended demand product A is December 3, the delivery time for the recommended supply product B is from December 1 to December 5, and the delivery time for the recommended supply product C is from December 5 to December 8, it can be seen that the demand deadline for the recommended demand product A (December 3) is later than the earliest delivery time point of the recommended supply product B (December 1). It can be determined that the demand deadline for the recommended demand product A matches the delivery time of the recommended supply product B, and whether other product attribute information of the recommended demand product A and the recommended supply product B matches can be further determined.

[0096] In addition, it can be seen that the demand deadline for the recommended demand product A (December 3) is earlier than the earliest delivery time point of the recommended supply product C (December 5). It can be judged that the demand deadline for the recommended demand product A does not match the delivery time of the recommended supply product C, and the supply and demand product pair can be directly not retained.

[0097] S303, determining whether the demand spot information and the supply spot information match.

[0098] If yes, execute step S304; if no, execute step S305.

[0099] In the embodiment of the present application, after determining whether the demand deadline and the delivery time match, it is possible to continue to determine whether the demand spot information and the supply spot information match. It is understandable that if the demand spot information and the supply spot information match, the supply and demand product pair can be retained. If the demand spot information and the supply spot information do not match, the supply and demand product pair is not retained.

[0100] Optionally, judging whether the demand spot information and the supply spot information match may include that if the demand spot information is spot and the supply spot information is non-spot, it can be judged that the demand spot information and the supply spot information do not match; if the demand spot information is spot and the supply spot information is spot, it can be judged that the demand spot information and the supply spot information match; if the demand spot information is non-spot, it can be directly judged that the demand spot information and the supply spot information match.

[0101] S304, retaining the supply and demand product pair.

[0102] S305: Do not retain the supply and demand product pair.

[0103] Therefore, this method can successively determine whether the demand price range and supply price range match, whether the demand deadline and delivery time match, and whether the demand spot information and supply spot information match, and screen out supply and demand product pairs with a high degree of matching from the three dimensions of price, delivery, and spot, which can effectively reduce the number of supply and demand product pairs, and then reduce the amount of calculation and improve the matching efficiency of supply and demand products.

[0104] Based on any of the above embodiments, Figure 4 As shown, calculating the product similarity score of the supply and demand product pair according to the first name of the demand product to be recommended and the second name of the supply product to be recommended may include:

[0105] S401, performing word segmentation processing on the first name and the second name respectively to obtain a plurality of word segments.

[0106] It is understandable that the product name may include multiple participles, and the first name and the second name may be separately processed to obtain multiple participles.

[0107] Optionally, multiple segmented words after the segmentation process are separated by spaces. For example, if the first name is "high-precision high-strength new type of automobile automatic door lock worm", the segmentation result may be "high-precision high-strength new type of automobile automatic door lock worm".

[0108] Optionally, a word segmentation processing platform may be used to perform word segmentation processing on the first name and the second name respectively to obtain a plurality of word segments. The word segmentation processing platform may be Jieba Library.

[0109] S402: Generate a first vector of the demand product to be recommended and a second vector of the supply product to be recommended according to the word segmentation.

[0110] Optionally, a term frequency-inverse document frequency (TF-IDF) method may be used to generate a first vector of the demand product to be recommended and a second vector of the supply product to be recommended according to word segmentation.

[0111] Specifically, the TF-IDF method is adopted to generate a first vector of the demand product to be recommended and a second vector of the supply product to be recommended according to the word segmentation, which may include calculating the first term frequency (Term Frequency, TF) of the word segmentation corresponding to the first name and the second term frequency of the word segmentation corresponding to the second name, and then calculating the first inverse document frequency (Inverse Document Frequency, IDF) of the word segmentation corresponding to the first name and the second inverse document frequency of the word segmentation corresponding to the second name, and then generating a first vector according to the first term frequency and the first inverse document frequency, and generating a second vector according to the second term frequency and the second inverse document frequency.

[0112] The following formula can be used to calculate the word frequency of the participle corresponding to the name: TF=P / Q, where P is the number of occurrences of a participle in the name, Q is the total number of participles included in the name, and TF is the word frequency of a participle in the name.

[0113] Among them, the following formula can be used to calculate the inverse document frequency of the word corresponding to the name: X is the total number of products, Y is the number of products containing a certain word, and IDF is the inverse document frequency of a certain word corresponding to the name.

[0114] Furthermore, the following formula may be used to generate a vector based on the term frequency and the inverse document frequency: TF-IDF=TF*IDF, where TF-IDF is a vector.

[0115] S403: Calculate a product similarity score based on the first vector and the second vector.

[0116] Optionally, calculating the product similarity score based on the first vector and the second vector may include calculating the cosine similarity between the first vector and the second vector, and generating the product similarity score based on the cosine similarity.

[0117] It is understandable that after calculating the cosine similarity between the first vector and the second vector, the cosine similarity can be used as the product similarity score, or the cosine similarity can be converted to generate the product similarity score.

[0118] For example, if the first name of the demand product A to be recommended is "high-precision and high-strength new automobile automatic door lock worm", the word segmentation processing result may be "high-precision and high-strength new automobile automatic door lock worm"; if the second name of the supply product B to be recommended is "automobile pneumatic high-temperature resistant and corrosion-resistant spring", the result after word segmentation processing is "automobile pneumatic high-temperature resistant and corrosion-resistant spring", then according to the TF-IDF method, the first vector of the demand product A to be recommended generated according to the word segmentation may be [0, 0.392, 0, 0.279, 0, 0, 0.392, 0.392, 0.392, 0.393], and the product similarity score between the demand product A and the supply product B may be 0.0935, and the product similarity between the demand product A and the supply product B is relatively low.

[0119] Therefore, the method can perform word segmentation on the first name and the second name respectively to obtain multiple word segments, generate a first vector of the demand product to be recommended and a second vector of the supply product to be recommended based on the word segmentation, and calculate the product similarity score based on the first vector and the second vector.

[0120] Based on any of the above embodiments, Figure 5 As shown, in step S104, generating a target supply-demand product pair list according to the product similarity score and the enterprise similarity score may include:

[0121] S501, selecting a target supply-demand product pair from the supply-demand product pairs according to the product similarity score and the enterprise similarity score.

[0122] Optionally, selecting a target supply-demand product pair from the supply-demand product pairs based on the product similarity score and the enterprise similarity score may include selecting candidate supply-demand product pairs from the supply-demand product pairs based on the product similarity score, and then selecting the target supply-demand product pair from the candidate supply-demand product pairs based on the enterprise similarity score.

[0123] Among them, selecting candidate supply-demand product pairs from the supply-demand product pairs according to the product similarity scores may include the following two possible implementation methods:

[0124] Method 1: Sort the product similarity scores from high to low, obtain the supply and demand product pairs corresponding to the top N product similarity scores, and use the supply and demand product pairs corresponding to the top N product similarity scores as candidate supply and demand product pairs.

[0125] Among them, N can be set according to actual conditions, for example, it can be set to 20.

[0126] This method can filter out the supply and demand product pairs with the top N product similarity scores from all supply and demand product pairs as candidate supply and demand product pairs.

[0127] Method 2: Obtain supply and demand product pairs corresponding to product similarity scores whose product similarity scores are greater than a preset threshold as candidate supply and demand product pairs.

[0128] The preset threshold value may be set according to actual conditions, for example, may be set to 0.8.

[0129] This method can filter out supply and demand product pairs whose product similarity scores are greater than a preset threshold from all supply and demand product pairs as candidate supply and demand product pairs.

[0130] Among them, selecting the target supply-demand product pair from the candidate supply-demand product pairs according to the enterprise similarity score may include the following two possible implementation methods:

[0131] Method 1: Sort the enterprise similarity scores from high to low, obtain the candidate supply and demand product pairs corresponding to the top N enterprise similarity scores, and use the candidate supply and demand product pairs corresponding to the top N enterprise similarity scores as the target supply and demand product pairs.

[0132] Among them, N can be set according to actual conditions, for example, it can be set to 20.

[0133] This method can screen out the top N supply and demand product pairs in terms of enterprise similarity scores from the candidate supply and demand product pairs as the target supply and demand product pairs.

[0134] Method 2: Obtain candidate supply-demand product pairs corresponding to enterprise similarity scores whose enterprise similarity scores are greater than a preset threshold, as target supply-demand product pairs.

[0135] The preset threshold value may be set according to actual conditions, for example, may be set to 0.8.

[0136] This method can screen out supply and demand product pairs whose enterprise similarity scores are greater than a preset threshold from candidate supply and demand product pairs as target supply and demand product pairs.

[0137] S502: Calculate the total similarity score of the target supply-demand product pair according to the product similarity score and the enterprise similarity score.

[0138] Optionally, calculating the total similarity score of the target supply-demand product pair based on the product similarity score and the enterprise similarity score may include obtaining weights corresponding to the product similarity score and the enterprise similarity score, and calculating the total similarity score of the target supply-demand product pair based on the product similarity score, the enterprise similarity score and the corresponding weights.

[0139] For example, the enterprise similarity score includes the enterprise credit score S cre , Enterprise Historical Preference Score his and enterprise transportation cost score S trafWhen calculating the total similarity score of the target supply and demand product pair based on the product similarity score, enterprise similarity score and corresponding weights, the following formula can be used:

[0140] S=a*S i +b*S cre +c*S his +d*S traf

[0141] Among them, S is the total similarity score of the target supply and demand product pair, S i is the product similarity score of the target supply and demand product pair, a, b, c, d are the product similarity scores S i , Corporate Credit Score cre , Enterprise Historical Preference Score his and enterprise transportation cost score S traf The corresponding weight.

[0142] S503: sort the target supply-demand product pairs according to the total similarity scores to generate a list of target supply-demand product pairs.

[0143] It can be understood that, the higher the total similarity score of the target supply-demand product pair, the higher the total similarity between the demand product to be recommended and the supply product to be recommended in the target supply-demand product pair.

[0144] Optionally, sorting the target supply and demand product pairs according to the total similarity score to generate a target supply and demand product pair list may include sorting the total similarity score from high to low, obtaining the target supply and demand product pairs corresponding to the top N total similarity scores, and generating a target supply and demand product pair list based on the target supply and demand product pairs corresponding to the top N total similarity scores. Wherein, N can be set according to actual conditions, for example, it can be set to 20. This method can filter out the target supply and demand product pairs with the top N total similarity scores from the target supply and demand product pairs, and then generate a target supply and demand product pair list.

[0145] Therefore, this method can screen out target supply and demand product pairs from the supply and demand product pairs according to the product similarity scores and the enterprise similarity scores, and calculate the total similarity scores of the target supply and demand product pairs according to the product similarity scores and the enterprise similarity scores, and then sort the target supply and demand product pairs according to the total similarity scores to generate a list of target supply and demand product pairs.

[0146] Figure 6 The present invention is a flowchart of a method for matching supply and demand products according to another embodiment of the present application.

[0147] like Figure 6 As shown, the method for matching supply and demand products in the embodiment of the present application may include the following steps:

[0148] S601, obtaining a supply-demand product pair, where the supply-demand product pair includes a demand product to be recommended and a supply product to be recommended.

[0149] S602: Calculate a product similarity score of the supply and demand product pair according to the first name of the demand product to be recommended and the second name of the supply product to be recommended.

[0150] S603: Select candidate supply-demand product pairs from the supply-demand product pairs according to the product similarity scores.

[0151] S604, calculating the enterprise credit score of the candidate supply and demand product pair.

[0152] For the relevant contents of steps S601-S604, please refer to the above embodiment, which will not be repeated here.

[0153] S605, determining whether the enterprise credit score is greater than a preset credit score threshold.

[0154] If yes, execute step S606; if no, execute step S611.

[0155] In the embodiment of the present application, it can be determined whether the enterprise credit score is greater than the preset credit score threshold. If the enterprise credit score is greater than the preset credit score threshold, it indicates that the enterprise has good reputation and low transaction risk, and the target supply and demand product pair can be screened from the candidate supply and demand product pairs according to the similarity scores of other enterprises. If the enterprise credit score is less than or equal to the preset credit score threshold, it indicates that the enterprise has poor reputation and high transaction risk, and the candidate supply and demand product pair can be directly not retained.

[0156] Among them, the preset credit score threshold can be set according to actual conditions.

[0157] S606, calculating the enterprise historical preference score of the candidate supply-demand product pair.

[0158] For the relevant content of step S606, please refer to the above embodiment, which will not be repeated here.

[0159] S607, determining whether the product is sensitive to transportation costs.

[0160] If yes, execute step S608; if no, execute step S609.

[0161] S608, calculating the enterprise transportation cost score of the candidate supply and demand product pairs.

[0162] S609: Calculate the total similarity score of the target supply-demand product pair according to the product similarity score and the enterprise similarity score.

[0163] In the embodiment of the present application, it is possible to determine whether a product is sensitive to transportation costs. If the product is sensitive to transportation costs, it is necessary to calculate the enterprise transportation cost score of the candidate supply and demand product pair. If the product is not sensitive to transportation costs, for example, when the product is a virtual product, it does not need to be transported, then it is not necessary to calculate the enterprise transportation cost score of the candidate supply and demand product pair.

[0164] It can be understood that when calculating the enterprise transportation cost score of a candidate supply and demand product pair, the total similarity score of the target supply and demand product pair can be calculated based on the product similarity score, enterprise credit score, enterprise historical preference score, and enterprise transportation cost score; when the enterprise transportation cost score of the candidate supply and demand product pair is not calculated, the total similarity score of the target supply and demand product pair can be calculated based on the product similarity score, enterprise credit score, and enterprise historical preference score.

[0165] S610: Sort the target supply-demand product pairs according to the total similarity scores to generate a target supply-demand product pair list.

[0166] S611, do not retain the candidate supply-demand product pair.

[0167] For the relevant contents of steps S610-S611, please refer to the above embodiment, which will not be repeated here.

[0168] In summary, according to the supply and demand product matching method of the embodiment of the present application, the product similarity score of the supply and demand product pair can be calculated, and candidate supply and demand product pairs can be screened out from the supply and demand product pairs according to the product similarity score. Then, the target supply and demand product pair can be screened out from the candidate supply and demand product pairs according to the enterprise credit score. Then, the total similarity score of the target supply and demand product pair can be calculated according to the product similarity score and the enterprise similarity score, and the target supply and demand product pairs can be sorted according to the total similarity score to generate a list of target supply and demand product pairs.

[0169] like Figure 7 As shown, in one embodiment of the present application, a supply and demand product matching system includes an input data module, an information extraction module, a data preprocessing module and a supply and demand matching module.

[0170] Among them, the input data module can be used to input product information data, enterprise information data, enterprise behavior data and geographic space data.

[0171] Among them, the information extraction module can be used to extract product attribute information such as keywords, dates, prices, and stock from product information data, and to extract information such as the company's credit rating from corporate information data. It can also be used to extract corporate historical click and browse data from corporate behavior data, and to extract location (such as longitude and latitude) and road conditions information from geographic spatial data.

[0172] Among them, the data preprocessing module is used to perform data preprocessing on product attribute information such as keywords, dates, prices, and spot prices to obtain product key information clustering, and is also used to perform data preprocessing on corporate credit ratings to obtain corporate credit rating classifications. It is also used to perform data preprocessing on corporate historical click and browse data to obtain corporate historical preference portraits, and is also used to perform data preprocessing on location (such as longitude and latitude) and road conditions information to obtain spatial distance.

[0173] Among them, the supply and demand matching module is used to calculate product similarity scores based on product key information clustering, and is also used to calculate enterprise similarity scores, including obtaining enterprise credit scores, enterprise historical preference scores, and enterprise transportation cost scores based on enterprise credit rating classification, enterprise historical preference portraits, and spatial distance. And the supply and demand product pair list can be obtained based on product similarity scores and enterprise similarity scores.

[0174] With the above Figures 1 to 7 Corresponding to the matching method of supply and demand products provided in the embodiment, the present disclosure also provides a matching device for supply and demand products. Figures 1 to 7 The matching method of supply and demand products provided in the embodiment corresponds to the embodiment, so the implementation method of the matching method of supply and demand products is also applicable to the matching device of supply and demand products provided in the embodiment of the present disclosure, and will not be described in detail in the embodiment of the present disclosure.

[0175] Figure 8 It is a schematic diagram of the structure of a device for matching supply and demand products according to an embodiment of the present application.

[0176] like Figure 8 As shown, the device 100 for matching supply and demand products according to the embodiment of the present application may include: an acquisition module 110 , a first calculation module 120 , a second calculation module 130 and a generation module 140 .

[0177] An acquisition module 110 is used to acquire a supply-demand product pair, wherein the supply-demand product pair includes a demand product to be recommended and a supply product to be recommended;

[0178] A first calculation module 120, used to calculate a product similarity score of the supply and demand product pair;

[0179] A second calculation module 130 is used to calculate the enterprise similarity score of the supply and demand product pair;

[0180] The generating module 140 is used to generate a target supply-demand product pair list according to the product similarity score and the enterprise similarity score.

[0181] In one embodiment of the present application, the enterprise similarity score includes at least one of the following scores: an enterprise credit score, an enterprise historical preference score, and an enterprise transportation cost score.

[0182] In one embodiment of the present application, the second calculation module 130 is specifically used to: obtain historical browsing click data of the enterprise corresponding to the supply and demand product pair; and calculate the historical preference score of the enterprise based on the historical browsing click data.

[0183] In one embodiment of the present application, the second calculation module 130 is specifically used to: obtain the spatial distance from the enterprise corresponding to the supply and demand product pair to the target enterprise; and calculate the enterprise transportation cost score based on the spatial distance.

[0184] In one embodiment of the present application, the generation module 140 is specifically used to: filter out target supply and demand product pairs from the supply and demand product pairs according to the product similarity scores and the enterprise similarity scores; calculate the total similarity scores of the target supply and demand product pairs according to the product similarity scores and the enterprise similarity scores; sort the target supply and demand product pairs according to the total similarity scores to generate the target supply and demand product pair list.

[0185] In one embodiment of the present application, the first calculation module 120 is specifically used to calculate the product similarity score of the supply and demand product pair according to the first name of the demand product to be recommended and the second name of the supply product to be recommended.

[0186] In one embodiment of the present application, Fig. 9 As shown, the first calculation module 120 includes: a word segmentation unit 1201, used to perform word segmentation on the first name and the second name respectively to obtain multiple word segments; a generation unit 1202, used to generate a first vector of the demand product to be recommended and a second vector of the supply product to be recommended according to the word segments; a calculation unit 1203, used to calculate the product similarity score according to the first vector and the second vector.

[0187] In one embodiment of the present application, the generating unit 1202 is specifically used to: calculate a first word frequency of the word segment corresponding to the first name and a second word frequency of the word segment corresponding to the second name; calculate a first inverse document frequency of the word segment corresponding to the first name and a second inverse document frequency of the word segment corresponding to the second name; generate the first vector according to the first word frequency and the first inverse document frequency; generate the second vector according to the second word frequency and the second inverse document frequency.

[0188] In one embodiment of the present application, the calculation unit 1203 is specifically used to: calculate the cosine similarity between the first vector and the second vector; and generate the product similarity score according to the cosine similarity.

[0189] In one embodiment of the present application, the acquisition module 110 is specifically used to: acquire first attribute information of the demand product and second attribute information of the supply product; and filter out the supply and demand product pairs from the demand product and the supply product based on the first attribute information and the second attribute information.

[0190] In one embodiment of the present application, the first attribute information includes at least one of the following information: demand price range, demand deadline and demand spot information; the second attribute information includes at least one of the following information: supply price range, delivery time and supply spot information.

[0191] In summary, the supply and demand product matching device of the embodiment of the present application obtains supply and demand product pairs, the supply and demand product pairs include demand products to be recommended and supply products to be recommended, calculates product similarity scores for the supply and demand product pairs, calculates enterprise similarity scores for the supply and demand product pairs, and generates a target supply and demand product pair list based on the product similarity scores and enterprise similarity scores. Thus, it is possible to comprehensively consider the impact of product similarity scores and enterprise similarity scores on supply and demand matching, and automatically generate a target supply and demand product pair list based on product similarity scores and enterprise similarity scores, so that enterprises can quickly and accurately obtain supply and demand product pairs with high product matching, which helps to improve the operational efficiency of enterprises.

[0192] In order to implement the above embodiment, Fig.10 As shown, the present application also proposes an electronic device 200, including: a memory 210, a processor 220, and a computer program stored in the memory 210 and executable on the processor 220. When the processor 220 executes the program, it implements the supply and demand product matching method proposed in the aforementioned embodiment of the present application.

[0193] The electronic device of the embodiment of the present application executes a computer program stored in a memory through a processor to obtain a supply and demand product pair, the supply and demand product pair includes a demand product to be recommended and a supply product to be recommended, calculates a product similarity score of the supply and demand product pair, calculates a corporate similarity score of the supply and demand product pair, and generates a target supply and demand product pair list based on the product similarity score and the corporate similarity score. Thus, the influence of the product similarity score and the corporate similarity score on the supply and demand matching can be comprehensively considered, and a target supply and demand product pair list can be automatically generated based on the product similarity score and the corporate similarity score, so that the enterprise can quickly and accurately obtain a supply and demand product pair with a high product matching degree, which helps to improve the operational efficiency of the enterprise.

[0194] In order to implement the above embodiments, the present application also proposes a computer-readable storage medium on which a computer program is stored. When the program is executed by a processor, the supply and demand product matching method proposed in the above embodiments of the present application is implemented.

[0195] The computer-readable storage medium of the embodiment of the present application obtains supply and demand product pairs by storing a computer program and being executed by a processor, wherein the supply and demand product pairs include demand products to be recommended and supply products to be recommended, calculates product similarity scores of the supply and demand product pairs, calculates enterprise similarity scores of the supply and demand product pairs, and generates a target supply and demand product pair list based on the product similarity scores and enterprise similarity scores. Thus, the influence of product similarity scores and enterprise similarity scores on supply and demand matching can be comprehensively considered, and a target supply and demand product pair list can be automatically generated based on product similarity scores and enterprise similarity scores, so that enterprises can quickly and accurately obtain supply and demand product pairs with high product matching, which helps to improve the operational efficiency of enterprises.

[0196] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present application. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner. In addition, those skilled in the art may combine and combine the different embodiments or examples described in this specification and the features of the different embodiments or examples, without contradiction.

[0197] In addition, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined as "first" and "second" may explicitly or implicitly include at least one of the features. In the description of this application, the meaning of "plurality" is at least two, such as two, three, etc., unless otherwise clearly and specifically defined.

[0198] Any process or method description in a flowchart or otherwise described herein may be understood to represent a module, fragment or portion of code comprising one or more executable instructions for implementing the steps of a custom logical function or process, and the scope of the preferred embodiments of the present application includes alternative implementations in which functions may not be performed in the order shown or discussed, including performing functions in a substantially simultaneous manner or in the reverse order depending on the functions involved, which should be understood by technicians in the technical field to which the embodiments of the present application belong.

[0199] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute the instructions), or in combination with these instruction execution systems, devices or apparatuses. For the purpose of this specification, "computer-readable medium" can be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in combination with these instruction execution systems, devices or apparatuses. More specific examples of computer-readable media (a non-exhaustive list) include the following: an electrical connection with one or more wires (electronic device), a portable computer disk box (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), a fiber optic device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium and then editing, interpreting or processing in other suitable ways if necessary, and then stored in a computer memory.

[0200] It should be understood that the various parts of the present application can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiments, multiple steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0201] A person skilled in the art may understand that all or part of the steps in the method for implementing the above-mentioned embodiment may be completed by instructing related hardware through a program, and the program may be stored in a computer-readable storage medium, which, when executed, includes one or a combination of the steps of the method embodiment.

[0202] In addition, each functional unit in each embodiment of the present application may be integrated into a processing module, or each unit may exist physically separately, or two or more units may be integrated into one module. The above-mentioned integrated module may be implemented in the form of hardware or in the form of a software functional module. If the integrated module is implemented in the form of a software functional module and sold or used as an independent product, it may also be stored in a computer-readable storage medium.

[0203] The storage medium mentioned above may be a read-only memory, a magnetic disk or an optical disk, etc. Although the embodiments of the present application have been shown and described above, it can be understood that the above embodiments are exemplary and cannot be understood as limiting the present application. A person of ordinary skill in the art may change, modify, replace and modify the above embodiments within the scope of the present application.

Claims

1. A method for matching supply and demand products, characterized in that: include: Obtaining a supply-demand product pair, the supply-demand product pair comprising a demand product to be recommended and a supply product to be recommended, wherein the demand product to be recommended is obtained from a product demander, and the supply product to be recommended is obtained from a product supplier, the product demander and the product supplier are both one or more, and the demand product to be recommended and the supply product to be recommended are both one or more; Calculating a product similarity score for the supply and demand product pair; Calculating a business similarity score for the supply and demand product pair; Generating a target supply-demand product pair list according to the product similarity score and the enterprise similarity score; The generating a target supply-demand product pair list according to the product similarity score and the enterprise similarity score comprises: Screening out a target supply-demand product pair from the supply-demand product pairs according to the product similarity score and the enterprise similarity score; Calculating a total similarity score of the target supply-demand product pair according to the product similarity score and the enterprise similarity score; The target supply-demand product pairs are sorted according to the total similarity score to generate a list of the target supply-demand product pairs.

2. The matching method according to claim 1, characterized in that: The enterprise similarity score includes at least one of the following scores: an enterprise credit score, an enterprise historical preference score, and an enterprise transportation cost score.

3. The matching method according to claim 2, characterized in that: Calculating the enterprise historical preference score for the supply and demand product pair, including: Obtain historical browsing and clicking data of the enterprise corresponding to the supply and demand product pair; The enterprise historical preference score is calculated based on the historical browsing click data.

4. The matching method according to claim 2, characterized in that: Calculating the enterprise transportation cost score of the supply and demand product pair, including: Obtain the spatial distance between the enterprise corresponding to the supply and demand product pair and the target enterprise; The enterprise transportation cost score is calculated according to the spatial distance.

5. The matching method according to claim 1, characterized in that: The calculating the product similarity score of the supply and demand product pair comprises: A product similarity score of the supply and demand product pair is calculated according to the first name of the demand product to be recommended and the second name of the supply product to be recommended.

6. The matching method according to claim 5, characterized in that: The calculating the product similarity score of the supply and demand product pair according to the first name of the demand product to be recommended and the second name of the supply product to be recommended includes: Performing word segmentation processing on the first name and the second name respectively to obtain a plurality of word segments; Generating a first vector of the demand product to be recommended and a second vector of the supply product to be recommended according to the word segmentation; The product similarity score is calculated based on the first vector and the second vector.

7. The matching method according to claim 6, characterized in that: The step of generating the first vector of the demand product to be recommended and the second vector of the supply product to be recommended according to the word segmentation includes: Calculate a first word frequency of the word segment corresponding to the first name and a second word frequency of the word segment corresponding to the second name; Calculate a first inverse document frequency of the word segment corresponding to the first name and a second inverse document frequency of the word segment corresponding to the second name; generating the first vector according to the first term frequency and the first inverse document frequency; The second vector is generated according to the second term frequency and the second inverse document frequency.

8. The matching method according to claim 6, characterized in that: The calculating the product similarity score according to the first vector and the second vector includes: Calculating the cosine similarity between the first vector and the second vector; The product similarity score is generated according to the cosine similarity.

9. The matching method according to claim 1, characterized in that: Also includes: Obtaining first attribute information of a demand product and second attribute information of a supply product; The supply-demand product pair is selected from the demand product and the supply product according to the first attribute information and the second attribute information.

10. The matching method according to claim 9, characterized in that: The first attribute information includes at least one of the following information: demand price range, demand deadline and demand spot information; The second attribute information includes at least one of the following information: supply price range, delivery time and supply spot information.

11. A device for matching supply and demand products, characterized in that: include: An acquisition module is used to acquire a supply-demand product pair, wherein the supply-demand product pair includes a demand product to be recommended and a supply product to be recommended, wherein the demand product to be recommended is acquired from a product demander, and the supply product to be recommended is acquired from a product supplier, the product demander and the product supplier are both one or more, and the demand product to be recommended and the supply product to be recommended are both one or more; A first calculation module, used to calculate the product similarity score of the supply and demand product pair; A second calculation module is used to calculate the enterprise similarity score of the supply and demand product pair; A generating module, used for generating a target supply-demand product pair list according to the product similarity score and the enterprise similarity score; The generating module is specifically used for: Screening out a target supply-demand product pair from the supply-demand product pairs according to the product similarity score and the enterprise similarity score; Calculating a total similarity score of the target supply-demand product pair according to the product similarity score and the enterprise similarity score; The target supply-demand product pairs are sorted according to the total similarity score to generate a list of the target supply-demand product pairs.

12. The matching device according to claim 11, characterized in that: The enterprise similarity score includes at least one of the following scores: an enterprise credit score, an enterprise historical preference score, and an enterprise transportation cost score.

13. The matching device according to claim 12, characterized in that: The second calculation module is specifically used for: Obtain historical browsing and clicking data of the enterprise corresponding to the supply and demand product pair; The enterprise historical preference score is calculated based on the historical browsing click data.

14. The matching device according to claim 12, characterized in that: The second calculation module is specifically used for: Obtain the spatial distance between the enterprise corresponding to the supply and demand product pair and the target enterprise; The enterprise transportation cost score is calculated according to the spatial distance.

15. The matching device according to claim 11, characterized in that: The first calculation module is specifically used for: A product similarity score of the supply and demand product pair is calculated according to the first name of the demand product to be recommended and the second name of the supply product to be recommended.

16. The matching device according to claim 15, characterized in that: The first calculation module includes: A word segmentation unit, used to perform word segmentation processing on the first name and the second name respectively to obtain a plurality of word segments; A generating unit, configured to generate a first vector of the demand product to be recommended and a second vector of the supply product to be recommended according to the word segmentation; A calculation unit is used to calculate the product similarity score according to the first vector and the second vector.

17. The matching device according to claim 16, characterized in that: The generating unit is specifically used for: Calculate a first word frequency of the word segment corresponding to the first name and a second word frequency of the word segment corresponding to the second name; Calculate a first inverse document frequency of the word segment corresponding to the first name and a second inverse document frequency of the word segment corresponding to the second name; generating the first vector according to the first term frequency and the first inverse document frequency; The second vector is generated according to the second term frequency and the second inverse document frequency.

18. The matching device according to claim 16, characterized in that: The computing unit is specifically used for: Calculating the cosine similarity between the first vector and the second vector; The product similarity score is generated according to the cosine similarity.

19. The matching device according to claim 11, characterized in that: The acquisition module is specifically used for: Obtaining first attribute information of a demand product and second attribute information of a supply product; The supply-demand product pair is selected from the demand product and the supply product according to the first attribute information and the second attribute information.

20. The matching device according to claim 19, characterized in that: The first attribute information includes at least one of the following information: demand price range, demand deadline and demand spot information; The second attribute information includes at least one of the following information: supply price range, delivery time and supply spot information.

21. An electronic device, characterized in that: The method comprises a memory, a processor and a computer program stored in the memory and executable on the processor. When the processor executes the program, the method for matching supply and demand products as described in any one of claims 1 to 10 is implemented.

22. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the supply-demand product matching method as described in any one of claims 1 to 10 is implemented.

Images